Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 650 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.7676. Min Act: -0.0001

Data Index: 633898 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.7551. Min Act: -0.0000

Data Index: 16354 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.8156. Min Act: -0.0001

Data Index: 1038395 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.7203. Min Act: -0.0001

Data Index: 1227329 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.7731. Min Act: -0.0001

Data Index: 744179 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.7184. Min Act: -0.0001

Data Index: 457881 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.7847. Min Act: -0.0001

Data Index: 1039371 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.6660. Min Act: -0.0000

Data Index: 772896 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.6789. Min Act: -0.0001

Data Index: 1204823 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.7415. Min Act: -0.0001

Data Index: 590679 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.7895. Min Act: -0.0000

Data Index: 776514 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.7548. Min Act: -0.0001

Data Index: 577369 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.6986. Min Act: -0.0000

Data Index: 614368 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.7692. Min Act: -0.0000

Data Index: 84905 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.7074. Min Act: -0.0000

Data Index: 782525 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.6633. Min Act: -0.0001

Data Index: 282384 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.7001. Min Act: -0.0001

Data Index: 1341543 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.7049. Min Act: -0.0000

Data Index: 218296 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.6421. Min Act: -0.0001

Data Index: 901726 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 0.8156. Min Range: -0.8156

Max Act: 0.6404. Min Act: -0.0000

Data Index: 491926 (C4 (Web Text))

Max Activating Token Index: 143